{"id":"https://openalex.org/W4401863723","doi":"https://doi.org/10.1145/3637528.3672051","title":"FaultInsight: Interpreting Hyperscale Data Center Host Faults","display_name":"FaultInsight: Interpreting Hyperscale Data Center Host Faults","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863723","doi":"https://doi.org/10.1145/3637528.3672051"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3672051","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3672051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059295946","display_name":"Tingzhu Bi","orcid":"https://orcid.org/0000-0003-0366-0410"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tingzhu Bi","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006129839","display_name":"Yang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang Yang","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037507957","display_name":"Yicheng Pan","orcid":"https://orcid.org/0000-0003-4139-1477"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Pan","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082859077","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-4334-5159"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762316","display_name":"Meng Ma","orcid":"https://orcid.org/0000-0002-1963-2513"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Ma","raw_affiliation_strings":["Peking University & Shuanghu Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University & Shuanghu Laboratory, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069364644","display_name":"Xinrui Jiang","orcid":"https://orcid.org/0000-0003-1591-0480"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinrui Jiang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037621362","display_name":"Linlin Han","orcid":"https://orcid.org/0000-0002-4714-2634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linlin Han","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071877363","display_name":"Feng Wang","orcid":"https://orcid.org/0009-0001-3981-8163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Wang","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002345641","display_name":"Xian Liu","orcid":"https://orcid.org/0000-0002-7332-0449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian Liu","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100338689","display_name":"Ping Wang","orcid":"https://orcid.org/0000-0002-8854-2079"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Wang","raw_affiliation_strings":["Peking University & Shuanghu Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University & Shuanghu Laboratory, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5059295946"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60345976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.7373743057250977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6525664329528809},{"id":"https://openalex.org/keywords/center","display_name":"Center (category theory)","score":0.5049973130226135},{"id":"https://openalex.org/keywords/data-center","display_name":"Data center","score":0.4586607813835144},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14545521140098572},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0663590133190155}],"concepts":[{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.7373743057250977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6525664329528809},{"id":"https://openalex.org/C2779463800","wikidata":"https://www.wikidata.org/wiki/Q5062222","display_name":"Center (category theory)","level":2,"score":0.5049973130226135},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.4586607813835144},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14545521140098572},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0663590133190155},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C8010536","wikidata":"https://www.wikidata.org/wiki/Q160398","display_name":"Crystallography","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3672051","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3672051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2028604378","https://openalex.org/W2033744149","https://openalex.org/W2035264666","https://openalex.org/W2045012623","https://openalex.org/W2085392455","https://openalex.org/W2161020850","https://openalex.org/W2169986380","https://openalex.org/W2181523240","https://openalex.org/W2775606259","https://openalex.org/W2900100055","https://openalex.org/W2908623803","https://openalex.org/W2913603385","https://openalex.org/W2944703101","https://openalex.org/W2962702521","https://openalex.org/W2972748364","https://openalex.org/W3006243790","https://openalex.org/W3112280859","https://openalex.org/W3133777397","https://openalex.org/W3161254931","https://openalex.org/W3174334998","https://openalex.org/W3179172661","https://openalex.org/W3196892655","https://openalex.org/W3217360279","https://openalex.org/W4286588841","https://openalex.org/W4290927880","https://openalex.org/W4364302701","https://openalex.org/W6791033905"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2379482911","https://openalex.org/W2645858920"],"abstract_inverted_index":{"Operating":[0],"and":[1,70],"maintaining":[2],"hyperscale":[3],"data":[4],"centers":[5],"involving":[6],"millions":[7],"of":[8,30,115,144],"service":[9],"hosts":[10],"has":[11],"been":[12],"an":[13],"extremely":[14],"intricate":[15],"task":[16],"to":[17,35,41,55,72,104,158],"tackle":[18],"for":[19],"top":[20],"Internet":[21],"companies.":[22],"Incessant":[23],"system":[24],"failures":[25],"cost":[26],"operators":[27],"countless":[28],"hours":[29],"browsing":[31],"through":[32],"performance":[33,68],"metrics":[34,69],"diagnose":[36],"the":[37,43,82,168,171],"underlying":[38],"root":[39,126],"cause":[40,127],"prevent":[42],"recurrence.":[44],"Although":[45],"many":[46],"state-of-the-art":[47],"(SOTA)":[48],"methods":[49],"have":[50],"used":[51],"time-series":[52],"causal":[53,57,92],"discovery":[54],"construct":[56],"relationships":[58],"among":[59],"anomalous":[60],"metrics,":[61],"they":[62],"only":[63],"focus":[64],"on":[65,76],"homogeneous":[66],"service-level":[67],"fail":[71],"yield":[73],"useful":[74],"insights":[75,100],"heterogeneous":[77],"host-level":[78],"metrics.":[79],"To":[80],"address":[81],"challenge,":[83],"this":[84],"study":[85],"presents":[86],"FaultInsight,":[87],"a":[88],"highly":[89],"interpretable":[90],"deep":[91],"host":[93],"fault":[94],"diagnosing":[95],"framework":[96],"that":[97],"offers":[98],"diagnostic":[99],"from":[101,118,161],"various":[102],"perspectives":[103],"reduce":[105],"human":[106],"effort":[107],"in":[108,133,142,146],"troubleshooting.":[109],"We":[110],"evaluate":[111],"FaultInsight":[112,122],"using":[113],"dozens":[114],"incidents":[116,160],"collected":[117],"our":[119,134],"production":[120,148],"environment.":[121],"provides":[123],"markedly":[124],"better":[125],"identification":[128],"accuracy":[129],"than":[130],"SOTA":[131],"baselines":[132],"incident":[135],"dataset.":[136],"It":[137],"also":[138],"shows":[139],"outstanding":[140],"advantages":[141],"terms":[143],"deployability":[145],"real":[147],"systems.":[149],"Our":[150],"engineers":[151],"are":[152],"deeply":[153],"impressed":[154],"by":[155],"FaultInsight's":[156],"ability":[157],"interpret":[159],"multiple":[162],"perspectives,":[163],"helping":[164],"them":[165],"quickly":[166],"understand":[167],"mechanism":[169],"behind":[170],"faults.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}